The growing adoption of Internet of Things (IoT) devices has amplified the need for robust security mechanisms, particularly against Denial of Service (DoS) and Distributed Denial of Service (DDoS) attacks. This paper proposes a deep learning-based detection system using a hybrid Convolutional Neural Network–Gated Recurrent Unit (CNN-GRU) model to effectively capture both spatial and temporal patterns of malicious activity. The CICDDoS2019 dataset is employed for training and evaluation, with preprocessing steps including Boruta-based feature selection and data rebalancing using SMOTE. A user-friendly GUI developed in Python (Tkinter) facilitates real-time input and prediction. The proposed model, Cyber Guard, demonstrates high accuracy and efficiency, offering a practical solution for IoT attack detection and future deployment.